Email processing for improved authentication question accuracy
Methods, systems, and apparatuses are described herein for improving the accuracy of authentication questions using e-mail processing. A request for access to an account may be received from a user device. A plurality of organizations may be identified. One or more e-mail associated with the account may be identified. The e-mails may be processed to identify one or more organizations that correspond to transactions conducted by a user. A modified plurality of organizations may be generated by removing, from the plurality of organizations, the one or more organizations. An authentication question may be generated and provided to the user device. A response to the authentication question may be received, and the user device may be provided access based on the response.
1. A method comprising:
receiving, from a user device, a request for access to an account associated with a user;
identifying a plurality of organizations by querying an organizations database;
receiving, from an e-mail server, one or more e-mails associated with the account;
processing the one or more e-mails using a machine learning model to identify one or more organizations, wherein the one or more organizations correspond to one or more transactions conducted by the user;
generating a modified plurality of organizations by removing, from the plurality of organizations, the one or more organizations;
generating an authentication question related to at least one of the modified plurality of organizations;
providing the authentication question to the user device;
receiving, from the user device, a response to the authentication question; and
providing, based on the response to the authentication question, the user device access to the account.
2. The method of claim 1 , wherein processing the one or more e-mails to identify the one or more organizations comprises:
determining an e-mail template corresponding to a first organization; and
identifying, based on comparing the e-mail template to at least one of the one or more e-mails, a second organization.
3. The method of claim 1 , wherein processing the one or more e-mails to identify the one or more organizations comprises:
training, using input data comprising a plurality of e-mails with tagged organizations, the machine learning model to identify indicators of organizations in e-mail data;
providing, as input to the machine learning model, the one or more e-mails; and
receiving, as output from the machine learning model, an indication of the one or more organizations.
4. The method of claim 1 , further comprising:
identifying, based on the one or more e-mails, a good or service, wherein generating the authentication question is based on the good or service.
5. The method of claim 1 , further comprising:
identifying, based on the one or more e-mails, an average expenditure associated with the user, wherein generating the authentication question is based on the average expenditure.
6. The method of claim 1 , wherein identifying the plurality of organizations comprises:
randomly selecting, from the organizations database, a predetermined quantity of organizations.
7. The method of claim 1 , further comprising:
identifying one or more aliases associated with the one or more organizations, wherein generating the modified plurality of organizations comprises removing, from the plurality of organizations and based on the one or more aliases, at least one of the plurality of organizations.
8. The method of claim 1 , wherein receiving the one or more e-mails associated with the account comprises:
querying the e-mail server for e-mails associated with a time period.
9. The method of claim 1 , wherein removing the one or more organizations comprises:
determining that a quantity of the modified plurality of organizations satisfies a threshold; and
adding, to the modified plurality of organizations, indicators of additional organizations.
10. A computing device comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the computing device to:
receive, from a user device, a request for access to an account associated with a user;
identify a plurality of organizations by querying an organizations database;
receive, from an e-mail server, one or more e-mails associated with the account;
process the one or more e-mails using a machine learning model to identify one or more organizations, wherein the one or more organizations correspond to one or more transactions conducted by the user;
generate a modified plurality of organizations by removing, from the plurality of organizations, the one or more organizations;
generate an authentication question related to at least one of the modified plurality of organizations; provide the authentication question to the user device;
receive, from the user device, a response to the authentication question; and
provide, based on the response to the authentication question, the user device access to the account.
11. The computing device of claim 10 , wherein the instructions, when executed by the one or more processors, cause the computing device to process the one or more e-mails to identify the one or more organizations by causing the computing device to:
determine an e-mail template corresponding to a first organization; and
identify, based on comparing the e-mail template to at least one of the one or more e-mails, a second organization.
12. The computing device of claim 10 , wherein the instructions, when executed by the one or more processors, cause the computing device to process the one or more e-mails to identify the one or more organizations by causing the computing device to:
train, using input data comprising a plurality of e-mails with tagged organizations, the machine learning model to identify indicators of organizations in e-mail data;
provide, as input to the machine learning model, the one or more e-mails; and
receive, as output from the machine learning model, an indication of the one or more organizations.
13. The computing device of claim 10 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
identify, based on the one or more e-mails, a good or service, wherein the instructions, when executed by the one or more processors, cause the computing device to generate the authentication question based on the good or service.
14. The computing device of claim 10 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
identify, based on the one or more e-mails, an average expenditure associated with the user, wherein the instructions, when executed by the one or more processors, cause the computing device to generate the authentication question based on the average expenditure.
15. The computing device of claim 10 , wherein the instructions, when executed by the one or more processors, cause the computing device to identify the plurality of organizations by causing the computing device to:
randomly select, from the organizations database, a predetermined quantity of organizations.
16. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause a computing device to:
receive, from a user device, a request for access to an account associated with a user;
identify a plurality of organizations by querying an organizations database;
receive, from an e-mail server, one or more e-mails associated with the account;
process the one or more e-mails using a machine learning model to identify one or more organizations, wherein the one or more organizations correspond to one or more transactions conducted by the user;
generate a modified plurality of organizations by removing, from the plurality of organizations, the one or more organizations;
generate an authentication question related to at least one of the modified plurality of organizations;
provide the authentication question to the user device;
receive, from the user device, a response to the authentication question; and
provide, based on the response to the authentication question, the user device access to the account.
17. The computer-readable media of claim 16 , wherein the instructions, when executed by the one or more processors, cause the computing device to process the one or more e-mails to identify the one or more organizations by causing the computing device to:
determine an e-mail template corresponding to a first organization; and
identify, based on comparing the e-mail template to at least one of the one or more e-mails, a second organization.
18. The computer-readable media of claim 16 , wherein the instructions, when executed by the one or more processors, cause the computing device to process the one or more e-mails to identify the one or more organizations by causing the computing device to:
train, using input data comprising a plurality of e-mails with tagged organizations, ft the machine learning model to identify indicators of organizations in e-mail data;
provide, as input to the machine learning model, the one or more e-mails; and
receive, as output from the machine learning model, an indication of the one or more organizations.
19. The computer-readable media of claim 16 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
identify, based on the one or more e-mails, a good or service, wherein the instructions, when executed by the one or more processors, cause the computing device to generate the authentication question based on the good or service.
20. The computer-readable media of claim 16 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
identify, based on the one or more e-mails, an average expenditure associated with the user, wherein the instructions, when executed by the one or more processors, cause the computing device to generate the authentication question based on the average expenditure.